Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aaebff0875e9d2ce285f40a1512de0dc475f86708e7ed3faa85f412582a044f
+size 59675008

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n    {%- if messages[0]['content'] is string -%}\n        {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n    {%- else -%}\n        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n    {%- endif -%}\n    {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n    {%- set first_user_prefix = \"\" -%}\n    {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n        {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n    {%- endif -%}\n    {%- if (message['role'] == 'assistant') -%}\n        {%- set role = \"model\" -%}\n    {%- else -%}\n        {%- set role = message['role'] -%}\n    {%- endif -%}\n    {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n    {%- if message['content'] is string -%}\n        {{ message['content'] | trim }}\n    {%- elif message['content'] is iterable -%}\n        {%- for item in message['content'] -%}\n            {%- if item['type'] == 'image' -%}\n                {{ '<start_of_image>' }}\n            {%- elif item['type'] == 'text' -%}\n                {{ item['text'] | trim }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{ raise_exception(\"Invalid content type\") }}\n    {%- endif -%}\n    {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{ '<start_of_turn>model\n' }}\n{%- endif -%}\n"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf5c7930cba565c7ccd0fa01f1ecfaa1ae21ef6e1f3a6e24c8ca65cc69a47e4
+size 30825092

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4981123ff3cf7bd5b7f76839e90e4776f747ca4c38dcb41876fa010c0dea8b23
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8545fe12be65f660e4c9651899b1fa228a8c8258cf276b1108a6dc112b990734
+size 1064

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3294117647058825,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023529411764705882,
+      "grad_norm": 6.661525726318359,
+      "learning_rate": 4e-05,
+      "loss": 3.1501,
+      "step": 1
+    },
+    {
+      "epoch": 0.047058823529411764,
+      "grad_norm": 7.423152446746826,
+      "learning_rate": 8e-05,
+      "loss": 3.4519,
+      "step": 2
+    },
+    {
+      "epoch": 0.07058823529411765,
+      "grad_norm": 7.344629764556885,
+      "learning_rate": 0.00012,
+      "loss": 3.2048,
+      "step": 3
+    },
+    {
+      "epoch": 0.09411764705882353,
+      "grad_norm": 8.129940032958984,
+      "learning_rate": 0.00016,
+      "loss": 3.1225,
+      "step": 4
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 6.877574443817139,
+      "learning_rate": 0.0002,
+      "loss": 2.9515,
+      "step": 5
+    },
+    {
+      "epoch": 0.1411764705882353,
+      "grad_norm": 4.28478479385376,
+      "learning_rate": 0.00019990453460620527,
+      "loss": 2.1975,
+      "step": 6
+    },
+    {
+      "epoch": 0.16470588235294117,
+      "grad_norm": 3.4814071655273438,
+      "learning_rate": 0.00019980906921241053,
+      "loss": 2.0311,
+      "step": 7
+    },
+    {
+      "epoch": 0.18823529411764706,
+      "grad_norm": 2.5042951107025146,
+      "learning_rate": 0.00019971360381861576,
+      "loss": 1.7222,
+      "step": 8
+    },
+    {
+      "epoch": 0.21176470588235294,
+      "grad_norm": 10.543612480163574,
+      "learning_rate": 0.00019961813842482102,
+      "loss": 1.601,
+      "step": 9
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 2.4977686405181885,
+      "learning_rate": 0.00019952267303102625,
+      "loss": 1.6609,
+      "step": 10
+    },
+    {
+      "epoch": 0.25882352941176473,
+      "grad_norm": 2.499239921569824,
+      "learning_rate": 0.0001994272076372315,
+      "loss": 1.4279,
+      "step": 11
+    },
+    {
+      "epoch": 0.2823529411764706,
+      "grad_norm": 1.3605753183364868,
+      "learning_rate": 0.00019933174224343676,
+      "loss": 1.4378,
+      "step": 12
+    },
+    {
+      "epoch": 0.3058823529411765,
+      "grad_norm": 2.2948458194732666,
+      "learning_rate": 0.00019923627684964202,
+      "loss": 1.4096,
+      "step": 13
+    },
+    {
+      "epoch": 0.32941176470588235,
+      "grad_norm": 1.9090344905853271,
+      "learning_rate": 0.00019914081145584725,
+      "loss": 1.38,
+      "step": 14
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 1.3216297626495361,
+      "learning_rate": 0.0001990453460620525,
+      "loss": 1.0872,
+      "step": 15
+    },
+    {
+      "epoch": 0.3764705882352941,
+      "grad_norm": 1.299048900604248,
+      "learning_rate": 0.00019894988066825777,
+      "loss": 1.0297,
+      "step": 16
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.3004589080810547,
+      "learning_rate": 0.00019885441527446303,
+      "loss": 0.9944,
+      "step": 17
+    },
+    {
+      "epoch": 0.4235294117647059,
+      "grad_norm": 1.202727198600769,
+      "learning_rate": 0.00019875894988066829,
+      "loss": 1.07,
+      "step": 18
+    },
+    {
+      "epoch": 0.4470588235294118,
+      "grad_norm": 1.67063570022583,
+      "learning_rate": 0.00019866348448687352,
+      "loss": 1.1953,
+      "step": 19
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.3096171617507935,
+      "learning_rate": 0.00019856801909307875,
+      "loss": 0.9428,
+      "step": 20
+    },
+    {
+      "epoch": 0.49411764705882355,
+      "grad_norm": 1.459935188293457,
+      "learning_rate": 0.000198472553699284,
+      "loss": 1.0548,
+      "step": 21
+    },
+    {
+      "epoch": 0.5176470588235295,
+      "grad_norm": 1.392005443572998,
+      "learning_rate": 0.00019837708830548927,
+      "loss": 0.9306,
+      "step": 22
+    },
+    {
+      "epoch": 0.5411764705882353,
+      "grad_norm": 1.4283812046051025,
+      "learning_rate": 0.00019828162291169452,
+      "loss": 0.9121,
+      "step": 23
+    },
+    {
+      "epoch": 0.5647058823529412,
+      "grad_norm": 1.283262014389038,
+      "learning_rate": 0.00019818615751789978,
+      "loss": 0.9064,
+      "step": 24
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.330345869064331,
+      "learning_rate": 0.000198090692124105,
+      "loss": 0.8008,
+      "step": 25
+    },
+    {
+      "epoch": 0.611764705882353,
+      "grad_norm": 1.3282525539398193,
+      "learning_rate": 0.00019799522673031027,
+      "loss": 0.7321,
+      "step": 26
+    },
+    {
+      "epoch": 0.6352941176470588,
+      "grad_norm": 1.2584058046340942,
+      "learning_rate": 0.00019789976133651553,
+      "loss": 0.7673,
+      "step": 27
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 1.2578104734420776,
+      "learning_rate": 0.00019780429594272076,
+      "loss": 0.7981,
+      "step": 28
+    },
+    {
+      "epoch": 0.6823529411764706,
+      "grad_norm": 1.4390983581542969,
+      "learning_rate": 0.00019770883054892602,
+      "loss": 0.8325,
+      "step": 29
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 1.6025103330612183,
+      "learning_rate": 0.00019761336515513128,
+      "loss": 0.8138,
+      "step": 30
+    },
+    {
+      "epoch": 0.7294117647058823,
+      "grad_norm": 1.480338215827942,
+      "learning_rate": 0.00019751789976133654,
+      "loss": 0.8751,
+      "step": 31
+    },
+    {
+      "epoch": 0.7529411764705882,
+      "grad_norm": 1.266036868095398,
+      "learning_rate": 0.00019742243436754177,
+      "loss": 0.7173,
+      "step": 32
+    },
+    {
+      "epoch": 0.7764705882352941,
+      "grad_norm": 1.233924150466919,
+      "learning_rate": 0.00019732696897374703,
+      "loss": 0.6959,
+      "step": 33
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.1584521532058716,
+      "learning_rate": 0.00019723150357995228,
+      "loss": 0.6162,
+      "step": 34
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 1.252702236175537,
+      "learning_rate": 0.00019713603818615754,
+      "loss": 0.5258,
+      "step": 35
+    },
+    {
+      "epoch": 0.8470588235294118,
+      "grad_norm": 1.3157094717025757,
+      "learning_rate": 0.0001970405727923628,
+      "loss": 0.7223,
+      "step": 36
+    },
+    {
+      "epoch": 0.8705882352941177,
+      "grad_norm": 1.310499668121338,
+      "learning_rate": 0.00019694510739856803,
+      "loss": 0.6344,
+      "step": 37
+    },
+    {
+      "epoch": 0.8941176470588236,
+      "grad_norm": 1.346976399421692,
+      "learning_rate": 0.00019684964200477326,
+      "loss": 0.7265,
+      "step": 38
+    },
+    {
+      "epoch": 0.9176470588235294,
+      "grad_norm": 1.2368614673614502,
+      "learning_rate": 0.00019675417661097852,
+      "loss": 0.6884,
+      "step": 39
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 1.3998883962631226,
+      "learning_rate": 0.00019665871121718378,
+      "loss": 0.7219,
+      "step": 40
+    },
+    {
+      "epoch": 0.9647058823529412,
+      "grad_norm": 1.2332427501678467,
+      "learning_rate": 0.00019656324582338904,
+      "loss": 0.7444,
+      "step": 41
+    },
+    {
+      "epoch": 0.9882352941176471,
+      "grad_norm": 1.0393794775009155,
+      "learning_rate": 0.0001964677804295943,
+      "loss": 0.5779,
+      "step": 42
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7419483661651611,
+      "learning_rate": 0.00019637231503579953,
+      "loss": 0.6714,
+      "step": 43
+    },
+    {
+      "epoch": 1.0235294117647058,
+      "grad_norm": 1.0514390468597412,
+      "learning_rate": 0.00019627684964200479,
+      "loss": 0.5436,
+      "step": 44
+    },
+    {
+      "epoch": 1.0470588235294118,
+      "grad_norm": 0.9511624574661255,
+      "learning_rate": 0.00019618138424821004,
+      "loss": 0.4626,
+      "step": 45
+    },
+    {
+      "epoch": 1.0705882352941176,
+      "grad_norm": 1.508288025856018,
+      "learning_rate": 0.00019608591885441527,
+      "loss": 0.5104,
+      "step": 46
+    },
+    {
+      "epoch": 1.0941176470588236,
+      "grad_norm": 1.4369169473648071,
+      "learning_rate": 0.00019599045346062053,
+      "loss": 0.6062,
+      "step": 47
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 1.1856215000152588,
+      "learning_rate": 0.0001958949880668258,
+      "loss": 0.5779,
+      "step": 48
+    },
+    {
+      "epoch": 1.1411764705882352,
+      "grad_norm": 1.317847490310669,
+      "learning_rate": 0.00019579952267303102,
+      "loss": 0.5041,
+      "step": 49
+    },
+    {
+      "epoch": 1.1647058823529413,
+      "grad_norm": 1.2989856004714966,
+      "learning_rate": 0.00019570405727923628,
+      "loss": 0.615,
+      "step": 50
+    },
+    {
+      "epoch": 1.188235294117647,
+      "grad_norm": 1.0592188835144043,
+      "learning_rate": 0.00019560859188544154,
+      "loss": 0.4445,
+      "step": 51
+    },
+    {
+      "epoch": 1.2117647058823529,
+      "grad_norm": 0.9522223472595215,
+      "learning_rate": 0.0001955131264916468,
+      "loss": 0.4166,
+      "step": 52
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 1.137998104095459,
+      "learning_rate": 0.00019541766109785206,
+      "loss": 0.5384,
+      "step": 53
+    },
+    {
+      "epoch": 1.2588235294117647,
+      "grad_norm": 1.0973365306854248,
+      "learning_rate": 0.0001953221957040573,
+      "loss": 0.4935,
+      "step": 54
+    },
+    {
+      "epoch": 1.2823529411764705,
+      "grad_norm": 1.0788564682006836,
+      "learning_rate": 0.00019522673031026252,
+      "loss": 0.4372,
+      "step": 55
+    },
+    {
+      "epoch": 1.3058823529411765,
+      "grad_norm": 1.1917812824249268,
+      "learning_rate": 0.00019513126491646778,
+      "loss": 0.5462,
+      "step": 56
+    },
+    {
+      "epoch": 1.3294117647058823,
+      "grad_norm": 1.1784740686416626,
+      "learning_rate": 0.00019503579952267303,
+      "loss": 0.5903,
+      "step": 57
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 1.0892928838729858,
+      "learning_rate": 0.0001949403341288783,
+      "loss": 0.4417,
+      "step": 58
+    },
+    {
+      "epoch": 1.3764705882352941,
+      "grad_norm": 1.2473161220550537,
+      "learning_rate": 0.00019484486873508355,
+      "loss": 0.6014,
+      "step": 59
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.3342103958129883,
+      "learning_rate": 0.00019474940334128878,
+      "loss": 0.4679,
+      "step": 60
+    },
+    {
+      "epoch": 1.423529411764706,
+      "grad_norm": 1.2751225233078003,
+      "learning_rate": 0.00019465393794749404,
+      "loss": 0.5651,
+      "step": 61
+    },
+    {
+      "epoch": 1.4470588235294117,
+      "grad_norm": 1.012502908706665,
+      "learning_rate": 0.0001945584725536993,
+      "loss": 0.29,
+      "step": 62
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.9788743257522583,
+      "learning_rate": 0.00019446300715990456,
+      "loss": 0.3741,
+      "step": 63
+    },
+    {
+      "epoch": 1.4941176470588236,
+      "grad_norm": 1.0560024976730347,
+      "learning_rate": 0.0001943675417661098,
+      "loss": 0.4329,
+      "step": 64
+    },
+    {
+      "epoch": 1.5176470588235293,
+      "grad_norm": 1.1424912214279175,
+      "learning_rate": 0.00019427207637231505,
+      "loss": 0.3667,
+      "step": 65
+    },
+    {
+      "epoch": 1.5411764705882351,
+      "grad_norm": 1.1789878606796265,
+      "learning_rate": 0.00019417661097852028,
+      "loss": 0.4384,
+      "step": 66
+    },
+    {
+      "epoch": 1.5647058823529412,
+      "grad_norm": 1.1614022254943848,
+      "learning_rate": 0.00019408114558472554,
+      "loss": 0.4265,
+      "step": 67
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 1.3976482152938843,
+      "learning_rate": 0.0001939856801909308,
+      "loss": 0.5109,
+      "step": 68
+    },
+    {
+      "epoch": 1.611764705882353,
+      "grad_norm": 1.1408592462539673,
+      "learning_rate": 0.00019389021479713605,
+      "loss": 0.4185,
+      "step": 69
+    },
+    {
+      "epoch": 1.6352941176470588,
+      "grad_norm": 1.242210030555725,
+      "learning_rate": 0.0001937947494033413,
+      "loss": 0.4089,
+      "step": 70
+    },
+    {
+      "epoch": 1.6588235294117646,
+      "grad_norm": 1.3533846139907837,
+      "learning_rate": 0.00019369928400954654,
+      "loss": 0.3804,
+      "step": 71
+    },
+    {
+      "epoch": 1.6823529411764706,
+      "grad_norm": 1.5269583463668823,
+      "learning_rate": 0.0001936038186157518,
+      "loss": 0.5357,
+      "step": 72
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 2.066941261291504,
+      "learning_rate": 0.00019350835322195703,
+      "loss": 0.6613,
+      "step": 73
+    },
+    {
+      "epoch": 1.7294117647058824,
+      "grad_norm": 1.3083280324935913,
+      "learning_rate": 0.0001934128878281623,
+      "loss": 0.3654,
+      "step": 74
+    },
+    {
+      "epoch": 1.7529411764705882,
+      "grad_norm": 1.0919277667999268,
+      "learning_rate": 0.00019331742243436755,
+      "loss": 0.3306,
+      "step": 75
+    },
+    {
+      "epoch": 1.776470588235294,
+      "grad_norm": 1.1151741743087769,
+      "learning_rate": 0.0001932219570405728,
+      "loss": 0.3895,
+      "step": 76
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.286359190940857,
+      "learning_rate": 0.00019312649164677804,
+      "loss": 0.4677,
+      "step": 77
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 1.03926682472229,
+      "learning_rate": 0.0001930310262529833,
+      "loss": 0.3884,
+      "step": 78
+    },
+    {
+      "epoch": 1.8470588235294119,
+      "grad_norm": 1.084747314453125,
+      "learning_rate": 0.00019293556085918855,
+      "loss": 0.4417,
+      "step": 79
+    },
+    {
+      "epoch": 1.8705882352941177,
+      "grad_norm": 1.1419929265975952,
+      "learning_rate": 0.0001928400954653938,
+      "loss": 0.4261,
+      "step": 80
+    },
+    {
+      "epoch": 1.8941176470588235,
+      "grad_norm": 1.1437164545059204,
+      "learning_rate": 0.00019274463007159907,
+      "loss": 0.4213,
+      "step": 81
+    },
+    {
+      "epoch": 1.9176470588235293,
+      "grad_norm": 1.0313295125961304,
+      "learning_rate": 0.0001926491646778043,
+      "loss": 0.3355,
+      "step": 82
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 1.3336807489395142,
+      "learning_rate": 0.00019255369928400956,
+      "loss": 0.4388,
+      "step": 83
+    },
+    {
+      "epoch": 1.9647058823529413,
+      "grad_norm": 1.2635568380355835,
+      "learning_rate": 0.0001924582338902148,
+      "loss": 0.4225,
+      "step": 84
+    },
+    {
+      "epoch": 1.988235294117647,
+      "grad_norm": 1.1508828401565552,
+      "learning_rate": 0.00019236276849642005,
+      "loss": 0.3403,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2531745433807373,
+      "learning_rate": 0.0001922673031026253,
+      "loss": 0.5257,
+      "step": 86
+    },
+    {
+      "epoch": 2.023529411764706,
+      "grad_norm": 0.7907515168190002,
+      "learning_rate": 0.00019217183770883057,
+      "loss": 0.1563,
+      "step": 87
+    },
+    {
+      "epoch": 2.0470588235294116,
+      "grad_norm": 0.8357899188995361,
+      "learning_rate": 0.00019207637231503583,
+      "loss": 0.2273,
+      "step": 88
+    },
+    {
+      "epoch": 2.070588235294118,
+      "grad_norm": 1.0556663274765015,
+      "learning_rate": 0.00019198090692124106,
+      "loss": 0.1731,
+      "step": 89
+    },
+    {
+      "epoch": 2.0941176470588236,
+      "grad_norm": 0.8954185843467712,
+      "learning_rate": 0.00019188544152744631,
+      "loss": 0.1575,
+      "step": 90
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 1.0291929244995117,
+      "learning_rate": 0.00019178997613365155,
+      "loss": 0.1907,
+      "step": 91
+    },
+    {
+      "epoch": 2.1411764705882352,
+      "grad_norm": 1.0664329528808594,
+      "learning_rate": 0.0001916945107398568,
+      "loss": 0.1823,
+      "step": 92
+    },
+    {
+      "epoch": 2.164705882352941,
+      "grad_norm": 1.1944317817687988,
+      "learning_rate": 0.00019159904534606206,
+      "loss": 0.2451,
+      "step": 93
+    },
+    {
+      "epoch": 2.1882352941176473,
+      "grad_norm": 1.3393555879592896,
+      "learning_rate": 0.00019150357995226732,
+      "loss": 0.2653,
+      "step": 94
+    },
+    {
+      "epoch": 2.211764705882353,
+      "grad_norm": 1.3618574142456055,
+      "learning_rate": 0.00019140811455847255,
+      "loss": 0.1786,
+      "step": 95
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 1.5982481241226196,
+      "learning_rate": 0.0001913126491646778,
+      "loss": 0.1967,
+      "step": 96
+    },
+    {
+      "epoch": 2.2588235294117647,
+      "grad_norm": 1.3369780778884888,
+      "learning_rate": 0.00019121718377088307,
+      "loss": 0.2106,
+      "step": 97
+    },
+    {
+      "epoch": 2.2823529411764705,
+      "grad_norm": 1.1570290327072144,
+      "learning_rate": 0.00019112171837708833,
+      "loss": 0.1624,
+      "step": 98
+    },
+    {
+      "epoch": 2.3058823529411763,
+      "grad_norm": 1.180243968963623,
+      "learning_rate": 0.00019102625298329359,
+      "loss": 0.1672,
+      "step": 99
+    },
+    {
+      "epoch": 2.3294117647058825,
+      "grad_norm": 1.218498945236206,
+      "learning_rate": 0.00019093078758949882,
+      "loss": 0.2139,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2583886078581696.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6641fc4903b882687d1567f21bf28aa9e327f0bc130f00693bc0bd7924100918
+size 5624